Road Traffic Anomaly Detection: A Survey

Manaa, Imane El; Benjelloun, Fadwa; Sabri, My Abdelouahed; Yahyaouy, Ali; Aarab, Abdellah

doi:10.1007/978-3-031-01942-5_77

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of this work showed that the type of intersection and the location variables are the main factors of the road conditions, that contribute most to road accident fatality. Manaa et al [15] used a study to evaluate different algorithms and techniques based on computer vision and artificial intelligence (AI) to monitor and detect traffic violations and outlined their advantages and disadvantages. To date, several studies have investigated road accidents, and various of them have assessed the efficacy of the empirical Bayesian technique on black spot classification.…”

Section: Introductionmentioning

confidence: 99%

Black spots identification on rural roads based on extreme learning machine

Mbarek

Jiber

Yahyaouy

et al. 2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Accident black spots are usually defined as road locations with a high risk of fatal accidents. A thorough analysis of these areas is essential to determine the real causes of mortality due to these accidents and can thus help anticipate the necessary decisions to be made to mitigate their effects. In this context, this study aims to develop a model for the identification, classification and analysis of black spots on roads in Morocco. These areas are first identified using extreme learning machine (ELM) algorithm, and then the infrastructure factors are analyzed by ordinal regression. The XGBoost model is adopted for weighted severity index (WSI) generation, which in turn generates the severity scores to be assigned to individual road segments. The latter are then classified into four classes by using a categorization approach (high, medium, low and safe). Finally, the bagging extreme learning machine is used to classify the severity of road segments according to infrastructures and environmental factors. Simulation results show that the proposed framework accurately and efficiently identified the black spots and outperformed the reputable competing models, especially in terms of accuracy 98.6%. In conclusion, the ordinal analysis revealed that pavement width, road curve type, shoulder width and position were the significant factors contributing to accidents on rural roads.</span>

show abstract

Section: Introductionmentioning

confidence: 99%